Advancing Automated Algorithm Design via Evolutionary Stagewise Design with LLMs
Chen Lu, Ke Xue, Chengrui Gao, Yunqi Shi, Siyuan Xu, Mingxuan Yuan, Chao Qian, Zhi-Hua Zhou

TL;DR
EvoStage introduces a stagewise, feedback-driven evolutionary framework utilizing LLMs for automated algorithm design, significantly outperforming existing methods in chip placement and optimization tasks.
Contribution
The paper presents EvoStage, a novel multi-stage evolutionary approach with real-time feedback and multi-agent systems, enhancing LLM-based algorithm design for industrial applications.
Findings
Outperforms human-expert and existing LLM methods in benchmarks.
Achieves state-of-the-art wire-length results on chip placement.
Surpasses original metrics in a commercial 3D chip placement tool.
Abstract
With the rapid advancement of human science and technology, problems in industrial scenarios are becoming increasingly challenging, bringing significant challenges to traditional algorithm design. Automated algorithm design with LLMs emerges as a promising solution, but the currently adopted black-box modeling deprives LLMs of any awareness of the intrinsic mechanism of the target problem, leading to hallucinated designs. In this paper, we introduce Evolutionary Stagewise Algorithm Design (EvoStage), a novel evolutionary paradigm that bridges the gap between the rigorous demands of industrial-scale algorithm design and the LLM-based algorithm design methods. Drawing inspiration from CoT, EvoStage decomposes the algorithm design process into sequential, manageable stages and integrates real-time intermediate feedback to iteratively refine algorithm design directions. To further reduce…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsVLSI and FPGA Design Techniques · Advanced Multi-Objective Optimization Algorithms · Metaheuristic Optimization Algorithms Research
